{"paper":{"title":"MT-WAM: Reorienting the One-Pass Predictive Representation Toward Action Generation","arxiv_id":"2609.21474","primary_cat":"cs.CV","submitted_at":"2026-09-18T08:23:15+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":0.98,"id":"s0","own":false,"role":"background","text":"Fast-WAM shows that video-action co-training improves control without generating future video at inference, making the representation from a single video diffusion Transformer forward central to action generation.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.13,"main_claim_p":0.17,"quantitative":false,"quantitative_p":0.17,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.01,"background":0.98,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.01}},{"i":1,"p":0.96,"id":"s1","own":false,"role":"gap","text":"However, future-observation prediction does not explicitly prioritize the future dynamics and visual structure needed for control.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.12,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.96,"method":0.0,"result":0.0,"background":0.04,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.9,"id":"s2","own":true,"role":"contribution","text":"We present MT-WAM, which retains the original training objectives and adds complementary supervision for future two-dimensional point trajectories and visual features.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.9,"main_claim_p":0.13,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.1,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.9,"interpretation":0.0}},{"i":3,"p":0.99,"id":"s3","own":true,"role":"method","text":"A lightweight dual-stream branch copied from the video backbone's final blocks provides target-specific processing, while a structured attention mask prevents cross-stream attention.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.87,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.99,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":4,"p":0.99,"id":"s4","own":true,"role":"method","text":"Motion-stream tokens supply additional dynamics conditions to the action expert.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.76,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.0,"method":0.99,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":5,"p":0.93,"id":"s5","own":true,"role":"method","text":"Future visual-feature prediction provides supervision in a feature space that captures object and spatial structure.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.82,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.93,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.06,"interpretation":0.01}},{"i":6,"p":0.8,"id":"s6","own":true,"role":"method","text":"This supervision trains the video backbone to provide more informative visual context for action generation under changing visual conditions, without adding visual-feature-stream tokens to action conditioning.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.87,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.8,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.06,"interpretation":0.14}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"method","text":"At inference, MT-WAM uses video and motion caches computed once per replan and skips future-video prediction.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.88,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":1.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":8,"p":1.0,"id":"s8","own":true,"role":"result","text":"Without additional embodied policy pretraining, MT-WAM achieves 98.2% success on LIBERO and 73.7% on LIBERO-Plus, exceeding Fast-WAM by 23.8 percentage points on the latter.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.51,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":9,"p":1.0,"id":"s9","own":true,"role":"result","text":"On RoboTwin 2.0 Clean2Rand, Random success increases from 6.30% to 19.40%; across four real-world tasks, average success increases from 67.0% to 77.8%.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.26,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.93,"text":"Without additional embodied policy pretraining, MT-WAM achieves 98.2% success on LIBERO and 73.7% on LIBERO-Plus, exceeding Fast-WAM by 23.8 percentage points on the latter.","location":"abstract s8","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":7555,"cost_usd_reported":0.0},"compiled_at":"2026-09-23","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.05,"states_limitation":0.26,"human_participants":0.03,"controlled_comparison":0.94,"randomized_assignment":0.03,"states_quantitative_result":0.99,"compares_with_prior_results":0.98,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":0.92,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":0.92,"simulation_or_computation":0.08}},"contribution_type":{"p":1.0,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":1.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":1.0,"text":"We present MT-WAM, which retains the original training objectives and adds complementary supervision for future two-dimensional point trajectories and visual features.","location":"abstract s2"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":10,"sentences_in_abstract":10},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}